Unauthorized callable execution via global name fallback
Published May 8, 2026 · Updated May 8, 2026
Unsafe reflection in PraisonAI before 4.6.37 and praisonaiagents before 1.6.37 allows remote attackers to invoke undeclared callables. ToolExecutionMixin.execute_tool falls back from declared tools and the registry to module globals and main, then directly calls the resolved name while the default permission allowlist is unset. Exploitation requires control of a tool-call name; the resulting callable runs with the application process privileges and can change state, expose data, or execute commands when a suitable helper is loaded.
Summary
What happened
Unsafe reflection in PraisonAI before 4.6.37 and praisonaiagents before 1.6.37 allows remote attackers to invoke undeclared callables. ToolExecutionMixin.execute_tool falls back from declared tools and the registry to module globals and main, then directly calls the resolved name while the default permission allowlist is unset. Exploitation requires control of a tool-call name; the resulting callable runs with the application process privileges and can change state, expose data, or execute commands when a suitable helper is loaded.
The record
- CVE
- CVE-2026-44339
- Published
- May 8, 2026
- Updated
- May 8, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-470
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- May 8, 2026CVE publishedPublication date reported by the CVE source.
- May 8, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=praisonai < 4.6.37
- Affected versionversion=praisonaiagents < 1.6.37
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-gmjg-hv98-qggq proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo